Microsoft testing Deep Search for Complex Queries

Microsoft today announced it is testing Deep Search, a new feature for its Bing search engine that aims to provide more comprehensive and relevant answers to complex queries.

Deep Search leverages GPT-4, a state-of-the-art generative AI language model, to better understand user intent and gather more relevant results from the web.

Deep Search works by expanding a user's search query into a more detailed description of what they are looking for. For instance, if a user searches for "how do points systems work in Japan," Deep Search might generate a more comprehensive description like:

"Provide an explanation of how various loyalty card programs work in Japan, including the benefits, requirements, and limitations of each. Include examples of popular loyalty cards from different categories, such as convenience stores, supermarkets, and restaurants. Show a comparison of the advantages and disadvantages of using loyalty cards versus other payment methods in Japan, including current rewards and benefits. Highlight the most popular services and participating merchants."

This expanded description captures the user's intent more accurately and allows Deep Search to find more relevant results from the web. According to Microsoft, Deep Search also uses a variety of ranking signals to ensure that the most relevant results are displayed first.

Deep Search is currently an experimental feature that is available to randomly selected users on Bing worldwide. Microsoft plans to make Deep Search more widely available in the future.

Key takeaways

• Deep Search is a new feature for Bing that provides more comprehensive and relevant answers to complex queries.
• Deep Search uses GPT-4 to understand user intent and gather more relevant results from the web.
• Deep Search is currently an experimental feature that is available to randomly selected users on Bing worldwide.